Search

In the context of electricity demand response, an important task is to generate accurate forecasts of energy loads for groups of households as well as individual consumers. We consider the problem of short-term (one-day-ahead) forecasting of the electricity consumption load of a residential building. In order to generate such forecasts, historical energy consumption data are used, presented in the form of a time series with a fixed time step. In this paper, we first review existing (one-day-ahead) forecasting methodologies including: a) naive persistence models, b) autoregressive-based models (e.g., AR and SARIMA), c) triple exponential smoothing (Holt-Winters) model, and d) combinations of naive persistence and auto-regressive-based models (PAR). We then introduce a novel forecasting methodology, namely seasonal persistence-based regressive model (SPR) that optimally selects between lower- and higher-frequency persistence and temporal dependencies that are specific to the residential electricity load profiles. Given that the proposed forecasting method equivalently translates into a regression optimization problem, recursive-least-squares is utilized to train the model in a computationally efficient manner. Finally, we demonstrate through simulations the forecasting accuracy of this method in comparison with the standard forecasting techniques (a)-(d).

We address the problem of trading energy flexibility, derived from pools of residential Photovoltaic and battery-storage systems, to the Day-ahead electricity market. By flexibility, we imply any additional energy that can be stored to or withdrawn from the participating batteries/households at a given time during the next day. The optimization variables include the selection/activation of a subset of participating batteries and the amount of flexibility that should be extracted. Furthermore, the optimization objective corresponds to the expected forecast revenues that can be generated by trading this flexibility to the Day-ahead electricity market. Given the high computationally complexity of a full scale optimization in the case of a large number of participating batteries, we propose a reinforcement-learning-based methodology, which admits linear complexity with the number of participating batteries. The proposed methodology advances prior work with respect to the integration of a large number of batteries. Furthermore, it extends prior work of the authors with respect to providing analytical performance guarantees in comparison with the baseline/nominal operation of the battery. Finally, we compare through simulations the performance of the proposed method with a Linear-Programming-based optimization that provides the exact optimum.

This paper considers a class of reinforcement-based learning (namely, perturbed learning automata) and provides a stochastic-stability analysis in repeatedly played, positive-utility, finite strategic-form games. Prior work in this class of learning dynamics primarily analyzes asymptotic convergence through stochastic approximations, where convergence can be associated with the limit points of an ordinary-differential equation (ODE). However, analyzing global convergence through an ODE-approximation requires the existence of a Lyapunov or a potential function, which naturally restricts the analysis to a fine class of games. To overcome these limitations, this paper introduces an alternative framework for analyzing asymptotic convergence that is based upon an explicit characterization of the invariant probability measure of the induced Markov chain. We further provide a methodology for computing the invariant probability measure in positive-utility games, together with an illustration in the context of coordination games. [ABSTRACT FROM AUTHOR]